VATEX

VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research. Contains over 41,250 videos and 825,000 captions in both English and Chinese, with over 206,000 English-Chinese parallel translation pairs. Supports multilingual video captioning and video-guided machine translation tasks.

Nova Lite from Amazon currently leads the VATEX leaderboard with a score of 0.778 across 2 evaluated AI models.

Paper
About this benchmark

What VATEX measures

VATEX is a multimodal benchmark that evaluates large language models on language, multimodal, video, and vision tasks. LLM Stats tracks 2 models on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.8, with the leader reaching 0.8.

Compare leaders on the best AI for language, best AI for multimodal, best AI for video and best AI for vision leaderboards.

Publication

Paper
VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research
Authors
Xin Wang, Jiawei Wu, Junkun Chen, Lei Li, and 2 others
Published

Abstract

We present a new large-scale multilingual video description dataset, VATEX, which contains over 41,250 videos and 825,000 captions in both English and Chinese. Among the captions, there are over 206,000 English-Chinese parallel translation pairs. Compared to the widely-used MSR-VTT dataset, VATEX is multilingual, larger, linguistically complex, and more diverse in terms of both video and natural language descriptions. We also introduce two tasks for video-and-language research based on VATEX: (1) Multilingual Video Captioning, aimed at describing a video in various languages with a compact unified captioning model, and (2) Video-guided Machine Translation, to translate a source language description into the target language using the video information as additional spatiotemporal context. Extensive experiments on the VATEX dataset show that, first, the unified multilingual model can not only produce both English and Chinese descriptions for a video more efficiently, but also offer improved performance over the monolingual models. Furthermore, we demonstrate that the spatiotemporal video context can be effectively utilized to align source and target languages and thus assist machine translation. In the end, we discuss the potentials of using VATEX for other video-and-language research.

AmazonNova Lite leads with 77.8%, followed by AmazonNova Pro at 77.8%.

Progress Over Time

Interactive timeline showing model performance evolution on VATEX

State-of-the-art frontier
Open
Proprietary

VATEX Leaderboard

2 models
ContextCostLicense
1
Amazon
Amazon
1
Amazon
Amazon
Notice missing or incorrect data?

FAQ

Common questions about VATEX.

What is the VATEX benchmark?

VaTeX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research. Contains over 41,250 videos and 825,000 captions in both English and Chinese, with over 206,000 English-Chinese parallel translation pairs. Supports multilingual video captioning and video-guided machine translation tasks.

What is the VATEX leaderboard?

The VATEX leaderboard ranks 2 AI models based on their performance on this benchmark. Currently, Nova Lite by Amazon leads with a score of 0.778. The average score across all models is 0.778.

What is the highest VATEX score?

The highest VATEX score is 0.778, achieved by Nova Lite from Amazon.

How many models are evaluated on VATEX?

2 models have been evaluated on the VATEX benchmark, with 0 verified results and 2 self-reported results.

Where can I find the VATEX paper?

The VATEX paper is available at https://arxiv.org/abs/1904.03493. The paper details the methodology, dataset construction, and evaluation criteria.

What categories does VATEX cover?

VATEX is categorized under language, multimodal, video, and vision. The benchmark evaluates multimodal models with multilingual support.

How recent are the VATEX leaderboard results?

The VATEX leaderboard was last updated in June 2026 and currently includes 2 evaluated models.

More evaluations to explore

Related benchmarks in the same category

View all language
MMLU-Pro

A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.

language
127 models
MMLU

Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains

language
100 models
Humanity's Last Exam

Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions

visionmultimodal
82 models
MMMU

MMMU (Massive Multi-discipline Multimodal Understanding) is a benchmark designed to evaluate multimodal models on college-level subject knowledge and deliberate reasoning. Contains 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering across 30 subjects and 183 subfields.

multimodalmultimodal
62 models
MMMU-Pro

A more robust multi-discipline multimodal understanding benchmark that enhances MMMU through a three-step process: filtering text-only answerable questions, augmenting candidate options, and introducing vision-only input settings. Achieves significantly lower model performance (16.8-26.9%) compared to original MMMU, providing more rigorous evaluation that closely mimics real-world scenarios.

multimodalmultimodal
56 models
MMMLU

Multilingual Massive Multitask Language Understanding dataset released by OpenAI, featuring professionally translated MMLU test questions across 14 languages including Arabic, Bengali, German, Spanish, French, Hindi, Indonesian, Italian, Japanese, Korean, Portuguese, Swahili, Yoruba, and Chinese. Contains approximately 15,908 multiple-choice questions per language covering 57 subjects.

language
48 models